关于covariance matrix 因变量的构建 [推广有奖]

15关注
26粉丝

学科带头人

77%

还不是VIP/贵宾

威望: 0 级
论坛币: 2319 个
通用积分: 28.6717
学术水平: 8 点
热心指数: 9 点
信用等级: 8 点
经验: 51435 点
帖子: 980
精华: 0
在线时间: 3788 小时
注册时间: 2010-4-3
最后登录: 2024-2-23

楼主

runman 发表于 2016-7-6 19:57:52 |只看作者 |坛友微信交流群|倒序 |AI写论文

是否 +2 论坛币

k人参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

数据为平行面板数据
code  time feature1 feature2  feature3  feature4  feature5 ...
1    1       ...          ...          ...          ...       ...       ...
...    ...    ...          ...          ...          ...       ...       ...
1    t       ...          ...          ...          ...       ...       ...
  2    1       ...          ...          ...          ...       ...       ...
...    ...    ...          ...          ...          ...       ...       ...
2    t       ...          ...          ...          ...       ...       ...
3    1       ...          ...          ...          ...       ...       ...
...    ...    ...          ...          ...          ...       ...       ...
3    t       ...          ...          ...          ...       ...       ...

   To recognize that particular combinations of features might mute or reinforce the impact of some of the others, we construct a covariance matrix of design features in which each variable is standardized to have
a mean of zero and a standard deviation of one.

   ......uses the first three principal component of the vector of design features as the endogenous variable......

   关于这一段的文字说明都看懂了，但是红色字体部分不知道是如何通过stata实现的？选择协方差矩阵向量的前3个主要成分作为因变量，具体的结构是怎样构成的？
          在此先谢谢啦^_^